面向对象和SVM结合的无人机数据建筑物提取

doi:10.6046/gtzyyg.2017.01.15

摘要
参考文献
相关文章
Metrics

全文: PDF(2804 KB)

HTML
输出: BibTeX | EndNote (RIS)

摘要

建筑物提取时结合归一化数字表面模型（nDSM）的高度信息可以提高其提取精度。通常高度信息由LiDAR数据生成高精度3D点云获得。但由于获取成本较高，寻找替代LiDAR点云生成高度信息的数据至关重要，为此该文探讨摄影测量点云生成nDSM用于建筑物提取的可适用性。采用无人机影像作为单一数据源，选取汉旺镇和林扒镇2个研究区进行实验，利用面向对象技术与支持向量机（SVM）相结合的方法进行建筑物提取。首先，采用Pix4D Mapper生成摄影测量点云，通过基于不规则三角网加密滤波方法和反距离加权法插值生成nDSM影像；其次，对无人机RGB影像进行分割，选取9种属性特征（2种高度属性和7种光谱属性）作为建筑物的识别属性；最后，利用SVM分类器进行建筑物提取，采用形态学滤波方法进行后处理。研究结果表明，汉旺研究区提取的完整率为85.5%，正确率为83.9%；林扒研究区提取的完整率为92.5%，正确率为78.6%。摄影测量点云生成的nDSM在建筑物提取应用中适用性较好，可以有效提高建筑物的提取精度，并且大大降低了成本。

	服务

	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	林娜
	杨武年
	王斌

关键词 ：高光谱遥感, 核方法, 混合像元分解, 正交子空间投影(OSP)

Abstract：

Height information created by LiDAR data is generally used for building extraction. LiDAR data can produce highly accurate, reliable 3D point clouds of ground objects. However, LiDAR data is expensive. In view of such a situation, this study aims to extract buildings solely using UAV imagery data. The height information used is created by point clouds derived from UAV stereo pairs through dense matching algorithm. In this study, UAV imagery was used as a single remote sensing data source and building extraction was carried out by the integration of objected-based method and SVM classification. In the preprocessing period, Pix4D Mapper was used for aerial triangulation and photogrammetric point clouds generation. Then, an objected-based method that utilized spectral information and geometric features was developed, the object height was derived from photogrammetric point clouds to assist in the detection of the building. Finally, the building boundaries were extracted through SVM classifier. In the post-processing procedure, morphological operations were applied to remove small objects from building images. To validate the photogrammetric point cloud usefulness, experiments were conducted on UAV imagery data, covering the selected test areas in Hanwang Town of Sichuan Province and Linpa Town of Henan Province. The building extraction accuracy was accessed on the test areas, and building detection completeness of Hanwang test area is 85.5%, detection correction is 83.9%; building detection completeness of Linpa test area is 92.5%, detection correction is 78.6%. The results show that nDSM derived from photogrammetric point clouds can be used for building extraction, and can improve the detection accuracy of the building.

Key words： hyperspectral remote sensing kernel trick pixel un-mixing orthogonal subspace projection (OSP)

收稿日期: 2015-09-18 出版日期: 2017-01-23

TP751.1

作者简介: 王旭东(1990-),男,硕士,主要从事无人机影像处理和三维建模研究。Email:wangxudong1304@163.com。

引用本文:

王旭东, 段福洲, 屈新原, 李丹, 余攀锋. 面向对象和SVM结合的无人机数据建筑物提取[J]. 国土资源遥感, 2017, 29(1): 97-103.
WANG Xudong, DUAN Fuzhou, QU Xinyuan, LI Dan, YU Panfeng. Building extraction based on UAV imagery data with the synergistic use of objected-based method and SVM classifier. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(1): 97-103.

链接本文:

https://www.gtzyyg.com/CN/10.6046/gtzyyg.2017.01.15 或 https://www.gtzyyg.com/CN/Y2017/V29/I1/97

[1] Ahmadi S,Zoej M J V,Ebadi H,et al.Automatic urban building boundary extraction from high resolution aerial images using an innovative model of active contours[J].International Journal of Applied Earth Observation and Geoinformation,2010,12(3):150-157.
[2] Turker M,Koc-San D.Building extraction from high-resolution optical spaceborne images using the integration of support vector machine(SVM) classification, Hough transformation and perceptual grouping[J].International Journal of Applied Earth Observation and Geoinformation,2015,34:58-69.
[3] 冯甜甜,龚健雅.基于LiDAR数据的建筑物自动提取方法的比较[J].测绘通报,2011(2):21-23,47. Feng T T,Gong J Y.Comparison of automatic building extraction methods based on LiDAR data[J].Bulletin of Surveying and Mapping,2011(2):21-23,47.
[4] Brunn A,Weidner U.Extracting buildings from digital surface models[J].International Archives of Photogrammetry and Remote Sensing,1997,32(3):27-34.
[5] Awrangjeb M,Ravanbakhsh M,Fraser C S.Automatic detection of residential buildings using LIDAR data and multispectral imagery[J].ISPRS Journal of Photogrammetry and Remote Sensing,2010,65(5):457-467.
[6] Sohn G,Dowman I.Data fusion of high-resolution satellite imagery and LiDAR data for automatic building extraction[J].ISPRS Journal of Photogrammetry and Remote Sensing,2007,62(1):43-63.
[7] Rottensteiner F,Trinder J,Clode S,et al.Building detection by fusion of airborne laser scanner data and multi-spectral images:Performance evaluation and sensitivity analysis[J].ISPRS Journal of Photogrammetry and Remote Sensing,2007,62(2):135-149.
[8] Kabolizade M,Ebadi H,Ahmadi S.An improved snake model for automatic extraction of buildings from urban aerial images and LiDAR data[J].Computers,Environment and Urban Systems,2010,34(5):435-441.
[9] Wei Y Z,Yao W,Wu J W,et al.Adaboost-based feature relevance assessment in fusing lidar and image data for classification of trees and vehicles in urban scenes[J].ISPRS Annals of Photogrammetry,Remote Sensing and Spatial Information Sciences,2012,I-7(7):323-328.
[10] Grigillo D,Kanjir U.Urban object extraction from digital surface model and digital aerial images[J].ISPRS Annals of Photogrammetry,Remote Sensing and Spatial Information Sciences,2012,I-3(3):215-220.
[11] Gerke M,Xiao J.Fusion of airborne laserscanning point clouds and images for supervised and unsupervised scene classification[J].ISPRS Journal of Photogrammetry and Remote Sensing,2014,87:78-92.
[12] Ke Y H,Quackenbush L J,Im J.Synergistic use of QuickBird multispectral imagery and LIDAR data for object-based forest species classification[J].Remote Sensing of Environment,2010,114(6):1141-1154.
[13] 汪小钦,王苗苗,王绍强,等.基于可见光波段无人机遥感的植被信息提取[J].农业工程学报,2015,31(5):152-159. Wang X Q,Wang M M,Wang S Q,et al.Extraction of vegetation information from visible unmanned aerial vehicle images[J].Transactions of the Chinese Society of Agricultural Engineering,2015,31(5):152-159.
[14] 何少林,徐京华,张帅毅.面向对象的多尺度无人机影像土地利用信息提取[J].国土资源遥感,2013,25(2):107-112.doi:10.6046/gtzyyg.2013.02.19. He S L,Xu J H,Zhang S Y.Land use classification of object-oriented multi-scale by UAV image[J].Remote Sensing for Land and Resources,2013,25(2):107-112.doi:10.6046/gtzyyg.2013.02.19.
[15] 雷添杰,李长春,何孝莹.无人机航空遥感系统在灾害应急救援中的应用[J].自然灾害学报,2011,20(1):178-183. Lei T J,Li C C,He X Y.Application of aerial remote sensing of pilotless aircraft to disaster emergency rescue[J].Journal of Natural Disasters,2011,21(1):178-183.
[16] 刘海飞,常庆瑞,李粉玲.高分辨率影像城区建筑物提取研究[J].西北农林科技大学学报:自然科学版, 201,413(10):221-227,234. Liu H F,Chang Q R,Li F L.Urban building extraction from high-resolution multi-spectral image with object-oriented classification[J].Journal of Northwest A&F University:Natural Science Edition,2013,41(10):221-227,234.
[17] Blaschke T,Hay G J,Kelly M,et al.Geographic object-based image analysis-towards a new paradigm[J].ISPRS Journal of Photogrammetry and Remote Sensing,2014,87(100):180-191.
[18] Khoshelham K,Nardinocchi C,Frontoni E,et al.Performance evaluation of automated approaches to building detection in multi-source aerial data[J].ISPRS Journal of Photogrammetry and Remote Sensing,2010,65(1):123-133.
[19] Dandois J P,Ellis E C.High spatial resolution three-dimensional mapping of vegetation spectral dynamics using computer vision[J].Remote Sensing of Environment,2013,136:259-276.
[20] Sithole G,Vosselman G.Experimental comparison of filter algorithms for bare-earth extraction from airborne laser scanning point clouds[J].ISPRS Journal of Photogrammetry and Remote Sensing,2004,59(1/2):85-101.
[21] 黄先锋,李卉,王潇,等.机载LiDAR数据滤波方法评述[J].测绘学报,2009,38(5):466-469. Huang X F,Li H,Wang X,et al.Filter algorithms of airborne LiDAR data:Review and prospects[J].Acta Geodaetica et Cartographica Sinica,2009,38(5):466-469.
[22] 黄金浪.基于TerraScan的LiDAR数据处理[J].测绘通报,2007(10):13-16. Huang J L.LiDAR data processing based on TerraScan[J].Bulletin of Surveying and Mapping,2007(10):13-16.
[23] Baatz M,Schäpe A.Multiresolution segmentation:An optimization approach for high quality multi-scale image segmentation[J].Angewandte Geographische Informationsverarbeitung XII,2000,58(3/4):12-23.
[24] Li D,Ke Y H,Gong H L,et al.Object-based urban tree species classification using bi-temporal WorldView-2 and WorldView-3 images[J].Remote Sensing,2015,7(12):16917-16937.
[25] Dash J,Steinle E,Singh R P,et al.Automatic building extraction from laser scanning data:An input tool for disaster management[J].Advances in Space Research,2004,33(3):317-322.
[26] Rau J Y,Jhan J P,Hsu Y C.Analysis of oblique aerial images for land cover and point cloud classification in an urban environment[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(3):1304-1319.
[27] Van Der Linden S,Janz A,Waske B,et al.Classifying segmented hyperspectral data from a heterogeneous urban environment using support vector machines[J].Journal of Applied Remote Sensing,2007,1(1):013543.
[28] Waske B,Benediktsson J A,Árnason K,et al.Mapping of hyperspectral AVIRIS data using machine-learning algorithms[J].Canadian Journal of Remote Sensing,2009,35(S1):S106-S116.
[29] Tigges J,Lakes T,Hostert P.Urban vegetation classification:Benefits of multitemporal RapidEye satellite data[J].Remote Sensing of Environment,2013,136:66-75.
[30] 梅建新.基于支持向量机的高分辨率遥感影像的目标检测研究[D].武汉:武汉大学,2004. Mei J X.Study on Object Detection for High Resolution Remote Sensing Images Based on Support Vector Machines[D].Wuhan:Wuhan University,2004.
[31] Rutzinger M,Rottensteiner F,Pfeifer N.A comparison of evaluation techniques for building extraction from airborne laser scanning[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2009,2(1):11-20.
[32] Chen Y W,Lin C J.Combining SVMs with Various Feature Selection Strategies[M]//Guyon I,Nikravesh M,Gunn S,et al,eds.Feature Extraction.Berlin Heidelberg:Springer,2006:315-324.

[1]	王茜, 任广利. 高光谱遥感异常信息在阿尔金索拉克地区铜金矿找矿工作中的应用[J]. 自然资源遥感, 2022, 34(1): 277-285.
[2]	高文龙, 张圣微, 林汐, 雒萌, 任照怡. 煤矿开采中SOM的遥感估算和时空动态分析[J]. 自然资源遥感, 2021, 33(4): 235-242.
[3]	姜亚楠, 张欣, 张春雷, 仲诚诚, 赵俊芳. 基于多尺度LBP特征融合的遥感图像分类[J]. 自然资源遥感, 2021, 33(3): 36-44.
[4]	臧传凯, 沈芳, 杨正东. 基于无人机高光谱遥感的河湖水环境探测[J]. 自然资源遥感, 2021, 33(3): 45-53.
[5]	胡新宇, 许章华, 陈文慧, 陈秋霞, 王琳, 刘辉, 刘智才. 基于PROBA/CHRIS影像的归一化阴影植被指数NSVI构建与应用效果[J]. 国土资源遥感, 2021, 33(2): 55-65.
[6]	张红利, 罗蔚然, 李艳. 基于粒子群优化和像元分解模型的遥感影像时空融合[J]. 国土资源遥感, 2020, 32(4): 33-40.
[7]	孙珂. 融合超像元与峰值密度特征的遥感影像分类[J]. 国土资源遥感, 2020, 32(4): 41-45.
[8]	秦其明, 陈晋, 张永光, 任华忠, 吴自华, 张赤山, 吴霖升, 刘见礼. 定量遥感若干前沿方向探讨[J]. 国土资源遥感, 2020, 32(4): 8-15.
[9]	王瑞军, 张春雷, 孙永彬, 王诜, 董双发, 王永军, 闫柏琨. 高光谱在甘肃红山多金属找矿模型构建中的应用[J]. 国土资源遥感, 2020, 32(3): 222-231.
[10]	朱爽, 张锦水. 时间序列低分影像修正中分遥感冬小麦分布[J]. 国土资源遥感, 2020, 32(1): 19-26.
[11]	张东辉, 赵英俊, 秦凯. 典型目标地面光谱信息系统设计与实现[J]. 国土资源遥感, 2018, 30(4): 206-211.
[12]	任广利, 杨敏, 李健强, 高婷, 梁楠, 易欢, 杨军录. 高光谱蚀变信息在金矿找矿预测中的应用研究——以北山方山口金矿线索为例[J]. 国土资源遥感, 2017, 29(3): 182-190.
[13]	苏红军, 刘浩. 一种利用空间和光谱信息的高光谱遥感多分类器动态集成算法[J]. 国土资源遥感, 2017, 29(2): 15-21.
[14]	张川, 叶发旺, 徐清俊, 刘洪成, 孟树. 新疆白杨河铀铍矿区航空高光谱矿物填图及蚀变特征分析[J]. 国土资源遥感, 2017, 29(2): 160-166.
[15]	林娜, 杨武年, 王斌. 基于核方法的高光谱遥感图像混合像元分解[J]. 国土资源遥感, 2017, 29(1): 14-20.

Viewed

Full text

Abstract

Cited

Shared

Discussed